A training-free method improves epistemic faithfulness of LLM textual explanations by guiding generation with attribution-based attention interventions.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 4roles
baseline 1polarities
baseline 1representative citing papers
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
CA-LIG is a unified hierarchical attribution method that computes layer-wise Integrated Gradients fused with class-specific attention gradients to generate signed, context-sensitive explanations for transformer models.
LRP-derived element-wise parameter importance scores gate gradients so parameters critical to earlier tasks receive smaller updates during continual LLM fine-tuning.
citing papers explorer
-
Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
A training-free method improves epistemic faithfulness of LLM textual explanations by guiding generation with attribution-based attention interventions.
-
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
-
Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
CA-LIG is a unified hierarchical attribution method that computes layer-wise Integrated Gradients fused with class-specific attention gradients to generate signed, context-sensitive explanations for transformer models.
-
Attribution-Guided Continual Learning for Large Language Models
LRP-derived element-wise parameter importance scores gate gradients so parameters critical to earlier tasks receive smaller updates during continual LLM fine-tuning.